<ul><li>Efficient resource management is critical for Non-Terrestrial Networks (NTNs) to provide consistent, high-quality service in remote and under-served regions.</li><li>Traditional single-point prediction methods, such as Long-Short Term Memory (LSTM), are insufficient for NTN resource allocation scenarios due to the complexity of satellite dynamics, signal latency, and coverage variability.</li><li>Probabilistic forecasting techniques, like SFF, are evaluated and found to be effective in predicting bandwidth and capacity requirements in different NTN segments.</li><li>The use of probabilistic forecasting models in integrated Terrestrial Network (TN)-NTN environments can optimize resource allocation by providing accurate and reliable predictions while quantifying uncertainty.</li></ul>

Probabilistic Forecasting for Network Resource Analysis in Integrated Terrestrial and Non-Terrestrial Networks

Discover more